Sodium battery energy storage system fault diagnosis method and device and storage medium

By using multiple physical circuit models and deep learning algorithms in the sodium battery energy storage system, the weighted feature matrix is ​​generated, which solves the problem of inaccurate fault diagnosis caused by a single model and improves the accuracy of fault diagnosis of sodium battery energy storage system. and reliability.

CN119087242APending Publication Date: 2024-12-06ZHUZHOU ELECTRIC LOCOMOTIVE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411423609.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-12
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing digital twin system of sodium battery energy storage system uses a single physical model and deep learning algorithm, resulting in inaccurate physical models and inappropriate neural network weight assignment under specific operating conditions, resulting in inaccurate fault diagnosis.

Method used

At least two physical circuit models are used to obtain basic monitoring data, and input them into the deep learning algorithm to generate a feature matrix. The fault diagnosis results are determined through the weighted fusion feature matrix, and the training data set is constructed based on historical monitoring data and fault logs to generate a fault diagnosis model. Reduce false alarms in a single subsystem.

Benefits of technology

By combining physical circuit models and deep learning algorithms, it is possible to capture the fault information of sodium battery energy storage system more comprehensively, improve the accuracy of fault diagnosis, reduce false alarms, and enhance the reliability of diagnostic results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119087242A_ABST
    Figure CN119087242A_ABST
Patent Text Reader

Abstract

The invention discloses a sodium battery energy storage system fault diagnosis method and device and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining a feature matrix of a sodium battery energy storage system based on at least two fault diagnosis subsystems combined by a physical circuit model and a deep learning algorithm; based on a weight matrix associated with fault diagnosis, performing weighted fusion on the features of the feature matrix to determine a fused feature; and determining a corresponding fault diagnosis result according to the fusion feature. By combining the physical circuit model and the deep learning algorithm, the fault information of the sodium battery energy storage system can be more comprehensively captured, the fault diagnosis result is determined through weighted fusion of the feature matrix, the false alarm situation generated by a single subsystem can be reduced, and the accuracy of fault diagnosis is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a fault diagnosis method, device and storage medium for a sodium battery energy storage system. Background Art

[0002] The current digital twin systems for monitoring sodium battery energy storage systems are all single digital twin systems, which are constructed using a single physical model and deep learning algorithm. This results in inaccurate physical models and inappropriate assignment of neural network neuron weights when facing specific working conditions, which in turn causes inaccurate fault diagnosis of the sodium battery energy storage system.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a method, device and computer-readable storage medium for constructing a digital twin system, aiming to solve the technical problem of how to improve the accuracy of fault diagnosis of sodium battery energy storage systems.

[0005] To achieve the above objectives, the present application proposes a sodium battery energy storage system fault diagnosis method, the method comprising: Obtain basic monitoring data based on at least two physical circuit models corresponding to the sodium battery energy storage system; Using the basic monitoring data corresponding to each of the physical circuit models as inputs of each deep learning algorithm associated with the sodium battery energy storage system to generate a feature matrix of the sodium battery energy storage system; If the fault diagnosis process is currently in progress, the feature matrix is ​​fused according to a first weight matrix associated with the fault diagnosis to obtain a fused feature; A corresponding fault diagnosis result is determined according to the fusion feature.

[0006] In one embodiment, the step of obtaining basic monitoring data based on at least two physical circuit models corresponding to the sodium battery energy storage system includes: Acquire the at least two physical circuit models constructed according to the working principle of the sodium battery energy storage system; The sodium battery energy storage system is monitored through the physical circuit model to obtain the basic monitoring data.

[0007] In one embodiment, if the fault diagnosis process is currently in progress, before the step of fusing the feature matrix according to the first weight matrix associated with the fault diagnosis to obtain the fused feature, the method includes: Construct a training dataset based on historical monitoring data and fault logs of the sodium battery energy storage system; A fault diagnosis model is trained according to the training data set to generate the first weight matrix.

[0008] In one embodiment, the step of constructing a training data set based on historical monitoring data and fault logs of the sodium battery energy storage system includes: Obtaining training input parameters of the physical circuit model; Based on the fault log, obtaining the historical fault diagnosis results corresponding to the training input parameters; A training data set is constructed according to the training input parameters and the historical fault diagnosis results.

[0009] In one embodiment, the step of using the basic monitoring data corresponding to each of the physical circuit models as inputs of each deep learning algorithm associated with the sodium battery energy storage system to generate a feature matrix of the sodium battery energy storage system includes: Preprocessing the basic monitoring data and inputting it into the deep learning algorithm; The features of the basic monitoring data are extracted through the deep learning algorithm to generate the feature matrix.

[0010] In one embodiment, if the fault diagnosis process is currently in progress, the step of fusing the feature matrix according to the first weight matrix associated with the fault diagnosis to obtain the fused feature includes: Obtaining the first weight matrix associated with the fault diagnosis; A matrix multiplication operation is performed on the feature matrix and the weight matrix to determine the fusion feature.

[0011] In one embodiment, before the step of determining the corresponding fault diagnosis result according to the fusion feature, the following steps are included: Constructing a life prediction subsystem to perform life prediction on the sodium battery energy storage system and obtain life prediction information; The historical operation data of the sodium battery energy storage system is collected, and the positive correlation between the life reduction and the failure rate of the sodium battery energy storage system is analyzed by statistical methods.

[0012] In one embodiment, the step of determining the corresponding fault diagnosis result according to the fusion feature includes: According to the positive correlation between the life reduction amount and the failure occurrence rate of the sodium battery energy storage system, calculating the failure occurrence rate corresponding to the life prediction information; A fault diagnosis result is determined based on the fault occurrence rate combined with the fusion feature.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a sodium battery energy storage system fault diagnosis device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the sodium battery energy storage system fault diagnosis method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the sodium battery energy storage system fault diagnosis method as described above are implemented.

[0015] The present application provides a sodium battery energy storage system fault diagnosis method. The present application firstly combines a physical circuit model and a deep learning algorithm to more comprehensively capture the fault information of the sodium battery energy storage system, and determines the fault diagnosis result by weighted fusion feature matrix, thereby reducing the false alarms generated by a single subsystem and improving the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the sodium battery energy storage system fault diagnosis method of the present application; Figure 2 A schematic diagram of a sodium battery energy storage system fault diagnosis system provided in Example 1 of the sodium battery energy storage system fault diagnosis method of the present application; Figure 3 A flow chart of the second embodiment of the sodium battery energy storage system fault diagnosis method provided in this application; Figure 4 A flow chart of the third embodiment of the sodium battery energy storage system fault diagnosis method of the present application; Figure 5 A schematic diagram of a sodium battery energy storage system life prediction system provided in Example 3 of the sodium battery energy storage system fault diagnosis method of the present application; Figure 6 Schematic diagram of the equipment structure of the hardware operating environment involved in the sodium battery energy storage system fault diagnosis method in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] The main solutions of the embodiments of this application are: At present, the digital twin systems for monitoring sodium battery energy storage systems are all single digital twin systems, which are constructed using a single physical model and deep learning algorithm. This leads to inaccurate physical models and inappropriate assignment of neural network neuron weights when facing specific working conditions, which in turn causes inaccurate fault diagnosis of the sodium battery energy storage system.

[0023] By combining physical circuit models and deep learning algorithms, this application can more comprehensively capture the fault information of the sodium battery energy storage system, determine the fault diagnosis results by weighted fusion feature matrices, reduce false alarms caused by a single subsystem, and improve the accuracy of fault diagnosis.

[0024] It should be noted that the execution subject of this embodiment can be a sodium battery energy storage system fault diagnosis system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a control device of a sodium battery energy storage system fault diagnosis system capable of realizing the above functions, etc., and this embodiment does not specifically limit this. The following takes the sodium battery energy storage system fault diagnosis system as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0025] Embodiment 1 Based on this, the present application proposes a sodium battery energy storage system fault diagnosis method of the first embodiment, please refer to Figure 1 , the sodium battery energy storage system fault diagnosis method comprises: Step S10: acquiring basic monitoring data based on at least two physical circuit models corresponding to the sodium battery energy storage system.

[0026] Through digital twin technology, a virtual circuit model is established for each device and component in the sodium battery energy storage system, and basic monitoring data is generated for deep learning algorithm input.

[0027] Optionally, in the process of constructing the physical circuit model corresponding to the sodium battery energy storage system, four stages are included: data preprocessing, modeling and simulation, digital twin model construction and monitoring data generation.

[0028] During the data processing stage, key parameter data such as voltage, current, temperature, humidity, vibration, etc. are collected from the actual operation of the sodium battery energy storage system. The collected data is cleaned, and missing data is processed by deletion, filling or interpolation. By comparing the unique identifier or content of the data, duplicate data records are found and deleted, and outliers in the data are identified. The outliers are deleted, replaced with reasonable values, or smoothed.

[0029] During the modeling and simulation stage, the structure and function of the digital twin model are designed according to actual needs. A detailed three-dimensional model of the digital twin model is established based on the sodium battery energy storage system through three-dimensional modeling software such as SolidWorks and AutoCAD. The three-dimensional model is dynamically simulated through simulation tools such as MATLAB and ANSYS to simulate the operating status and performance of equipment and components under different working conditions. The simulation results are determined and organized to ensure a unified format.

[0030] During the digital twin model construction phase, key information from the simulation results is extracted and mapped to the corresponding parts of the digital twin model. The preprocessed data and simulation results are integrated into the digital twin model to form a complete virtual model. The constructed digital twin model is verified and the model is optimized and improved based on the verification results.

[0031] In the monitoring data generation stage, the type and format of the input data are determined according to the requirements of the deep learning algorithm, the collected data is converted into the required format, features useful for the analysis algorithm are extracted from the input data, and the feature subset that contributes most to the analysis algorithm is determined through feature selection methods. Standardization or normalization is performed to remove dimensional differences and numerical range differences between different features and determine the basic monitoring data.

[0032] Optionally, step S10 includes: Step S11, obtaining the at least two physical circuit models constructed according to the working principle of the sodium battery energy storage system.

[0033] Construct a physical circuit model of the sodium battery energy storage system, and accurately describe and simulate the electrical behavior and working characteristics of the sodium battery energy storage system through mathematical models and circuit theory.

[0034] In this embodiment, the physical circuit model refers to a mathematical model established according to the electrical characteristics and working principles of the sodium battery energy storage system, which simulates the electrical behavior of the system under normal and fault conditions and outputs relevant electrical characteristic parameters.

[0035] Exemplarily, according to the actual circuit structure of the sodium battery energy storage system, circuit elements are selected to construct a physical circuit model, and according to the electrical connection method and functional requirements of the sodium battery energy storage system, the topological structure of the physical circuit model is designed. Based on circuit theory and mathematical models, mathematical equations are established for each element in the physical circuit model and the entire system.

[0036] Step S12, monitoring the sodium battery energy storage system through the physical circuit model to obtain the basic monitoring data, including battery voltage, current, temperature, charge state, health state and other parameters.

[0037] In this embodiment, basic monitoring data refers to basic data reflecting the operating status and performance of the battery obtained through monitoring.

[0038] Exemplarily, according to the characteristics of the physical circuit model and the requirements of the sodium battery energy storage system, the parameters to be monitored are set, the sodium battery energy storage system is monitored through the physical circuit model, and basic monitoring data is obtained.

[0039] Step S20, using the basic monitoring data corresponding to each of the physical circuit models as inputs of each deep learning algorithm associated with the sodium battery energy storage system to generate a feature matrix of the sodium battery energy storage system.

[0040] By combining two different technical means, physical circuit model and deep learning algorithm, characteristic information that can reflect the operating status and potential faults of the sodium battery energy storage system is extracted, and this characteristic information is represented in the form of a characteristic matrix.

[0041] In this embodiment, the deep learning algorithm is a machine learning method that automatically identifies fault-related features by simulating the structure and function of the human brain neural network, including convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM), etc. The feature matrix is ​​used to store and represent feature information extracted from the data, where each row represents a circuit feature extracted from a physical circuit model, and each column represents a data feature captured by a deep learning algorithm.

[0042] Optionally, step S20 includes: Step S21, preprocessing the basic monitoring data and inputting it into the deep learning algorithm.

[0043] In this embodiment, preprocessing refers to performing processing operations such as cleaning, normalization, and feature extraction on basic monitoring data to improve the quality of the data.

[0044] Exemplarily, outliers in basic monitoring data are checked for deletion and replacement, missing data are processed using interpolation filling methods, the data are scaled to a uniform scale using a min-max normalization method to eliminate dimensional differences between different features, and the processed data are input into a deep learning algorithm.

[0045] Step S22: extracting the features of the basic monitoring data through the deep learning algorithm to generate the feature matrix.

[0046] Exemplarily, various deep learning algorithms are used to train and learn the preprocessed data to extract complex data features, and the extracted features are arranged in a matrix form according to the correspondence between the basic monitoring data and the features.

[0047] Step S30: If the current process is a fault diagnosis process, the feature matrix is ​​fused according to a first weight matrix associated with the fault diagnosis to obtain a fused feature.

[0048] Through weighted fusion, the importance of different features in fault diagnosis is comprehensively considered, so that the fused features can better reflect the actual state and potential faults of the circuit.

[0049] In this embodiment, the elements in the weight matrix represent the weights of different features in the fault diagnosis process. Weighted fusion is a data processing technology that performs weighted summation of features in the feature matrix according to the weights of each feature in the weight matrix to generate a new fusion feature.

[0050] Optionally, step S30 includes: Step S31, obtaining the first weight matrix associated with the fault diagnosis.

[0051] For example, refer to Figure 2 , input the basic monitoring data detected by circuit model 1 to circuit model n into deep learning algorithm 1 to deep learning algorithm n, extract feature information, and apply Dempster's rule to fuse feature information according to DS evidence fusion theory (Dempster-Shafer Evidence Theory). For any two features m1 and m2, we can use Dempster's rule to calculate their fusion results m(A)=(m1⊕m2)(A) / (1-K). Among them, A is a proposition in the recognition framework, ⊕ represents the orthogonal sum operation, and K is the conflict coefficient (i.e., the orthogonal sum between m1 and m2), which is used to evaluate the inconsistency between them. If K is close to 1, it means that there is a serious conflict between m1 and m2; if K is close to 0, it means that the consistency between them is high. The features are normalized by the softmax function to obtain the digital twin weight value and determine the first weight matrix.

[0052] Step S32, performing matrix multiplication operation on the feature matrix and the weight matrix to determine the fusion feature.

[0053] The importance of each feature in fault diagnosis is comprehensively evaluated, and a new feature set is generated that can more comprehensively and accurately reflect the system status and faults.

[0054] In this embodiment, matrix multiplication is a basic mathematical operation that follows specific rules to calculate the product of two matrices, and the fused features are obtained by multiplying the features in the feature matrix with the corresponding weights in the weight matrix.

[0055] As an optional implementation, by analyzing historical fault data, using statistical methods to calculate the weight of each feature, and constructing a weight matrix, ensuring that the dimensions of the weight matrix and the feature matrix match, performing matrix multiplication operations, and obtaining the weighted sum of the features in the feature matrix and the corresponding weights in the weight matrix, that is, the fused features.

[0056] Step S40: determining a corresponding fault diagnosis result according to the fusion feature.

[0057] Based on the comprehensive information carried by the fusion features, the fault diagnosis algorithm is used to achieve accurate diagnosis of system faults.

[0058] In this embodiment, the fused features are features obtained after feature extraction and weighted fusion processing.

[0059] Optionally, step S40 includes: Step S41, calculating the failure rate corresponding to the life prediction information according to the positive correlation between the life reduction amount and the failure rate of the sodium battery energy storage system.

[0060] In this embodiment, the life reduction refers to the degree to which the life of the sodium battery energy storage system is shortened due to various factors during use. The failure rate refers to the probability of failure of the sodium battery energy storage system within a certain period of time.

[0061] Exemplarily, historical data of the sodium battery energy storage system is collected, including the life reduction and the corresponding failure rate, and a positive correlation model between the life reduction and the failure rate is established using statistical methods to obtain life prediction information of the sodium battery energy storage system. The life prediction information is input into the positive correlation model to calculate the corresponding failure rate.

[0062] Step S42: determining a fault diagnosis result based on the fault occurrence rate and the fusion feature.

[0063] In this embodiment, the fault diagnosis result is information about the system fault obtained through a fault diagnosis algorithm based on information such as the fault occurrence rate and fusion characteristics.

[0064] Exemplarily, current fault information of the sodium battery energy storage system is determined based on the fusion characteristics, and the fault diagnosis result is obtained by combining the fault occurrence rate with the current fault information.

[0065] This embodiment provides a sodium battery energy storage system fault diagnosis method. This embodiment firstly combines the physical circuit model and the deep learning algorithm to more comprehensively capture the fault information of the sodium battery energy storage system, and determines the fault diagnosis result by weighted fusion feature matrix, which can reduce the false alarms generated by a single subsystem and improve the accuracy of fault diagnosis.

[0066] Based on Example 1, Example 2 of the present application proposes a sodium battery energy storage system fault diagnosis method, referring to Figure 3 , before step S30, including: Step S50: construct a training data set based on historical monitoring data and fault logs of the sodium battery energy storage system.

[0067] In this embodiment, the fault log is the data recorded when the sodium battery energy storage system fails in the past period of time, including information such as fault type, time, location, and related parameters. The comprehensive fault score is a quantitative indicator calculated based on a statistical analysis method, which is used to evaluate the influence of specific features on the occurrence of faults in historical fault data. The training data set is a data set used to train machine learning or deep learning models, which contains input features and corresponding fault types.

[0068] Optionally, step S50 includes: Step S51, obtaining training input parameters of the physical circuit model.

[0069] In this embodiment, the training input parameters include: The timeliness of fault detection uses the time from the prediction of a fault to the actual occurrence of the fault as the timeliness indicator of fault detection. The longer the time, the better the timeliness of fault detection. The sensitivity of fault detection sets a threshold for each battery state parameter. If the threshold is exceeded by 100%, it is considered a fault. The state parameter value captured when the fault occurs is compared with the threshold. The smaller the ratio, the higher the sensitivity of fault detection. The false alarm rate, missed alarm rate, and detection rate of fault detection: reporting a fault when there is no fault is a false alarm, not reporting a fault when it occurs is a missed alarm, and correctly predicting the occurrence of a fault is a detection.

[0070] Step S52: Based on the fault log, obtain the historical fault diagnosis results corresponding to the training input parameters.

[0071] Exemplarily, the fault logs of the sodium battery are collected and sorted, and the historical fault diagnosis results in the fault logs are matched with the training input parameters to obtain the historical fault diagnosis results corresponding to the training input parameters.

[0072] Step S53: constructing a training data set according to the training input parameters and the historical fault diagnosis results.

[0073] In this embodiment, the training data set is a data set including a plurality of training samples, each training sample being composed of a training input parameter and a corresponding historical fault result.

[0074] Step S60: training a fault diagnosis model according to the training data set to generate the first weight matrix.

[0075] In this embodiment, the fault diagnosis model is a deep learning model that predicts device faults based on input parameters. The first weight matrix is ​​used to store the importance between the input features and the output labels.

[0076] Exemplarily, a training data set is input into the model for model training, and the value of the weight matrix is ​​continuously adjusted during the training process. After the training is completed, the weight matrix is ​​constructed.

[0077] The present embodiment provides a sodium battery energy storage system fault diagnosis method. The present embodiment firstly integrates historical monitoring data and fault logs to construct a training data set containing a large amount of actual operation data and fault cases, so that the model can learn more fault characteristics and laws, and improve the generalization ability of the model. The fault diagnosis model is trained using the training data set that has been preprocessed and feature extracted, which significantly improves the prediction performance of the model and improves the efficiency of fault diagnosis.

[0078] Based on Example 1, Example 3 of the present application proposes a sodium battery energy storage system fault diagnosis method, referring to Figure 4 , before step S40, including: Step S70, constructing a life prediction subsystem to perform life prediction on the sodium battery energy storage system and obtain life prediction information.

[0079] In this embodiment, the life prediction subsystem is a system for predicting the life of the sodium battery energy storage system. Based on the deep learning algorithm, it predicts performance changes by analyzing the historical operation data of the battery. The life reduction refers to the degree of life reduction experienced by the sodium battery energy storage system during use when its performance gradually decreases until it cannot meet specific performance requirements. It is used to quantify the degree of battery aging.

[0080] For example, refer to Figure 5, collect the life prediction information of the single digital twin system for the sodium battery energy storage system, and evaluate the accuracy of the sodium battery life prediction of the single digital twin system according to the actual value and the predicted value through evaluation indicators such as MSE (Mean Square Error), RMSE (Root Mean Square Error) and R² (R-squared, determination coefficient), apply the DS evidence fusion theory, fuse the evaluation indicators according to the Dempster rule, obtain the comprehensive evaluation indicators to adjust and optimize the model parameters, input the new operation data into the trained model, perform life prediction, and output the life prediction information DT=σ1DT1+σ2DT2+…+σnDTn. Among them, DT (Digital Twin) is the life prediction information of the single digital twin system for life prediction, which is the weighted sum of multiple components such as DT1, DT2, DTn, and each component is preceded by a corresponding weight coefficient σ1, σ2, σn, etc.

[0081] Step S80, collecting historical operation data of the sodium battery energy storage system, and analyzing the positive correlation between the life reduction and the failure rate of the sodium battery energy storage system by statistical methods.

[0082] In this embodiment, the positive correlation refers to a relationship between two variables, where an increase in one variable will lead to an increase in the other variable, and an increase in the life reduction will lead to an increase in the failure rate.

[0083] Exemplarily, historical operating data of the sodium battery energy storage system is collected, and preprocessing operations such as cleaning, denoising, and normalization are performed on the collected data. Statistical methods are used to analyze the positive correlation between life reduction and failure rate, and the relationship between the two is intuitively displayed by calculating the correlation coefficient.

[0084] The present embodiment provides a sodium battery energy storage system fault diagnosis method. The present embodiment first analyzes the positive correlation between the life reduction and the fault occurrence rate to deeply understand the relationship between the performance degradation and fault occurrence of the sodium battery energy storage system, thereby accurately performing fault diagnosis of the sodium battery energy storage system.

[0085] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the fault diagnosis method of the sodium battery energy storage system of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0086] The present application provides a sodium battery energy storage system fault diagnosis device, the sodium battery energy storage system fault diagnosis device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sodium battery energy storage system fault diagnosis method in the above-mentioned embodiment 1.

[0087] Reference below Figure 6 , which shows a schematic diagram of the structure of a sodium battery energy storage system fault diagnosis device suitable for implementing the embodiment of the present application. The sodium battery energy storage system fault diagnosis device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The sodium battery energy storage system fault diagnosis device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0088] like Figure 6As shown, the sodium battery energy storage system fault diagnosis device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the sodium battery energy storage system fault diagnosis device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the sodium battery energy storage system fault diagnosis device to communicate wirelessly or wired with other devices to exchange data. Although the sodium battery energy storage system fault diagnosis device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0089] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0090] The sodium battery energy storage system fault diagnosis device provided by the present application adopts the sodium battery energy storage system fault diagnosis method in the above embodiment, which can solve the technical problem of how to improve the accuracy of fault diagnosis of the sodium battery energy storage system. Compared with the prior art, the beneficial effects of the sodium battery energy storage system fault diagnosis device provided by the present application are the same as the beneficial effects of the sodium battery energy storage system fault diagnosis method provided by the above embodiment, and the other technical features of the sodium battery energy storage system fault diagnosis device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0091] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0092] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0093] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the sodium battery energy storage system fault diagnosis method in the above-mentioned embodiment.

[0094] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0095] The computer-readable storage medium may be included in the sodium battery energy storage system fault diagnosis device; or may exist independently without being assembled into the sodium battery energy storage system fault diagnosis device.

[0096] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the sodium battery energy storage system fault diagnosis device, the sodium battery energy storage system fault diagnosis device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0097] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0098] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0099] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned sodium battery energy storage system fault diagnosis method, and can solve the technical problem of how to improve the accuracy of fault diagnosis of the sodium battery energy storage system. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the sodium battery energy storage system fault diagnosis method provided in the above-mentioned embodiment, and will not be repeated here.

[0100] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A sodium battery energy storage system fault diagnosis method, characterized in that: The method includes: Obtain basic monitoring data based on at least two physical circuit models corresponding to the sodium battery energy storage system; Using the basic monitoring data corresponding to each of the physical circuit models as inputs of each deep learning algorithm associated with the sodium battery energy storage system to generate a feature matrix of the sodium battery energy storage system; If the fault diagnosis process is currently in progress, the feature matrix is ​​fused according to a first weight matrix associated with the fault diagnosis to obtain a fused feature; A corresponding fault diagnosis result is determined according to the fusion feature.

2. The sodium battery energy storage system fault diagnosis method according to claim 1, characterized in that: The step of obtaining basic monitoring data based on at least two physical circuit models corresponding to the sodium battery energy storage system includes: Acquire the at least two physical circuit models constructed according to the working principle of the sodium battery energy storage system; The sodium battery energy storage system is monitored through the physical circuit model to obtain the basic monitoring data.

3. The sodium battery energy storage system fault diagnosis method according to claim 1, characterized in that: Before the step of fusing the feature matrix to obtain the fused feature according to the first weight matrix associated with the fault diagnosis if the fault diagnosis process is currently in progress, the method includes: Construct a training dataset based on historical monitoring data and fault logs of the sodium battery energy storage system; A fault diagnosis model is trained according to the training data set to generate the first weight matrix.

4. The sodium battery energy storage system fault diagnosis method according to claim 3, characterized in that: The step of constructing a training data set based on historical monitoring data and fault logs of the sodium battery energy storage system includes: Obtaining training input parameters of the physical circuit model; Based on the fault log, obtaining the historical fault diagnosis results corresponding to the training input parameters; A training data set is constructed according to the training input parameters and the historical fault diagnosis results.

5. The sodium battery energy storage system fault diagnosis method according to claim 1, characterized in that: The step of using the basic monitoring data corresponding to each of the physical circuit models as inputs of each deep learning algorithm associated with the sodium battery energy storage system to generate a feature matrix of the sodium battery energy storage system comprises: Preprocessing the basic monitoring data and inputting it into the deep learning algorithm; The features of the basic monitoring data are extracted through the deep learning algorithm to generate the feature matrix.

6. The sodium battery energy storage system fault diagnosis method according to claim 1, characterized in that: If the fault diagnosis process is currently in progress, the step of fusing the feature matrix according to the first weight matrix associated with the fault diagnosis to obtain the fused feature comprises: Obtaining the first weight matrix associated with the fault diagnosis; A matrix multiplication operation is performed on the feature matrix and the weight matrix to determine the fusion feature.

7. The sodium battery energy storage system fault diagnosis method according to claim 1, characterized in that: Before the step of determining the corresponding fault diagnosis result according to the fusion feature, the method includes: Constructing a life prediction subsystem to perform life prediction on the sodium battery energy storage system and obtain life prediction information; The historical operation data of the sodium battery energy storage system is collected, and the positive correlation between the life reduction and the failure rate of the sodium battery energy storage system is analyzed by statistical methods.

8. The sodium battery energy storage system fault diagnosis method according to claim 1, characterized in that: The step of determining the corresponding fault diagnosis result according to the fusion feature comprises: According to the positive correlation between the life reduction amount and the failure occurrence rate of the sodium battery energy storage system, calculating the failure occurrence rate corresponding to the life prediction information; A fault diagnosis result is determined based on the fault occurrence rate combined with the fusion feature.

9. A sodium battery energy storage system fault diagnosis device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the sodium battery energy storage system fault diagnosis method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the sodium battery energy storage system fault diagnosis method according to any one of claims 1 to 8 are implemented.